RESUMEN

Although studies used machine learning algorithms to predict performances in sports activities, none, to the best of our knowledge, have used and validated two artificial intelligence techniques: artificial neural network (ANN) and k-nearest neighbor (KNN) in the running discipline of marathon and compared the accuracy or precision of the predicted performances. Official French rankings for the 10-km road and marathon events in 2019 were scrutinized over a dataset of 820 athletes (aged 21, having run 10 km and a marathon in the same year that was run slower, etc.). For the KNN and ANN the same inputs (10-km race time, body mass index, age and sex) were used to solve a linear regression problem to estimate the marathon race time. No difference was found between the actual and predicted marathon performances for either method (p>0,05). All predicted performances were significantly correlated with the actual ones, with very high correlation coefficients (r>0,90; p<0,001). KNN outperformed ANN with a mean absolute error of 2,4 vs 5,6%. The study confirms the validity of both algorithms, with better accuracy for KNN in predicting marathon performance. Consequently, the predictions from these artificial intelligence methods may be used in training programs and competitions.

Asunto(s)

RESUMEN

PURPOSE: The registration of a preoperative 3D model, reconstructed, for example, from MRI, to intraoperative laparoscopy 2D images, is the main challenge to achieve augmented reality in laparoscopy. The current systems have a major limitation: they require that the surgeon manually marks the occluding contours during surgery. This requires the surgeon to fully comprehend the non-trivial concept of occluding contours and surgeon time, directly impacting acceptance and usability. To overcome this limitation, we propose a complete framework for object-class occluding contour detection (OC2D), with application to uterus surgery. METHODS: Our first contribution is a new distance-based evaluation score complying with all the relevant performance criteria. Our second contribution is a loss function combining cross-entropy and two new penalties designed to boost 1-pixel thickness responses. This allows us to train a U-Net end to end, outperforming all competing methods, which tends to produce thick responses. Our third contribution is a dataset of 3818 carefully labelled laparoscopy images of the uterus, which was used to train and evaluate our detector. RESULTS: Evaluation shows that the proposed detector has a similar false false-negative rate to existing methods but substantially reduces both false-positive rate and response thickness. Finally, we ran a user study to evaluate the impact of OC2D against manually marked occluding contours in augmented laparoscopy. We used 10 recorded gynecologic laparoscopies and involved 5 surgeons. Using OC2D led to a reduction of 3 min and 53 s in surgeon time without sacrificing registration accuracy. CONCLUSIONS: We provide a new set of criteria and a distance-based measure to evaluate an OC2D method. We propose an OC2D method which outperforms the state-of-the-art methods. The results obtained from the user study indicate that fully automatic augmented laparoscopy is feasible.

Asunto(s)

RESUMEN

We aimed at studying the effect of Motor Imagery (MI), i.e., the mental representation of a movement without executing it, on breath-holding performance. Classical guidelines for efficient MI interventions advocate for a congruent MI practice with regards to the requirements of the physical performance, specifically in terms of physiological arousal. We specifically aimed at studying whether an incongruent form of MI practice might enhance the breath-hold performance. In a counterbalanced design including three experimental sessions, participants engaged in maximal breath-hold trials while concomitantly performing i) MI of breathing, ii) MI of breath-hold, and iii) an "ecological" breath-hold trial, i.e., without specific instructions of MI practice. In addition to breath-hold durations, we measured the cardiac activity and blood oxygen saturation. Performance was improved during MI of breathing (73.06 s ±â€¯24.53) compared to both MI of breath-hold (70.57 s ±â€¯18.15) and the control condition (67.67 s ±â€¯19.27) (p < 0.05). The mechanisms underlying breath-hold performance improvements during MI of breathing remain uncertain. MI of breathing might participate to decrease the threat perception associated with breath-holding, presumably due to psychological and physiological effects associated with the internal simulation of a breathing body state.

Asunto(s)

RESUMEN

The aim of the present work was to propose a Smartphone algorithm to analyze, in real time, the evolution of Heart Rate Variability (HRV) in order to individualize and reduce the recording time according to the specificities of each user. During HRV recording, a new RMSSD value is calculated each time a new RR is captured. The recording process stops once an acceptable stability of HRV is reached. This new method was tested on 3 groups of 15 subjects (cardiac patients, sedentary employees and national-level athletes) and compared with the gold standard method (5 min HRV recording time). The RMSSD indices provided by the short method and by the gold standard method (respectively 62.1 ± 43.7 ms vs. 62.7 ± 44.1 ms) showed no significant differences. In addition, a very strong correlation was observed between RMSSD values obtained by the 2 methods (n = 45; R = 0.998; p < 0.001). Routine duration of the new method was significantly shorter with a time-savings of 2 min (178 ± 51 s vs. 300 s; p < 0.05). This new algorithm seems to adapt perfectly to each subject, and it can detect the stability phase for HRV measurements during the recording process. Algorithm provides an adapted and personal routine duration that can evolve each day depending on parameters such as fatigue or stress level that are known to influence HRV. This solution can be easily implemented in a smartphone application and seems particularly suitable for performing daily HRV monitoring in field conditions.

Asunto(s)

RESUMEN

BACKGROUND: To examine pacing among twelve males on a 75-km mountain ultra marathon (MUM) and to determine whether pacing relates to final performance. METHODS: Speed and heart rates (HR) were measured continuously using a HR monitor and a global position system device. An Index of Pacing (IP) was calculated by dividing the average race speed by the speed on the first race segment. In addition, percentage (%) of heart rate reserve (HRres), coefficient of variation (CV) in speed and in percentage of HRres were analyzed throughout the race. RESULTS: Performance time was correlated with IP (r=-0.88, P<0.01), % of HRres (r=- 0.72, P<0.05), and CV in % of HRres (r=0.80, P<0.05), but not with CV in speed (r=-0.12, P=0.9). On the entire race, evolution of HR was not dependent on the elevation gain. CONCLUSIONS: Tracking HR is a safer way to rate pacing than speed tracking on a hilly course.

Asunto(s)

RESUMEN

Physical inactivity and sedentary behaviors are on the rise worldwide and contribute to the current overweight and obesity scourge. The loss of healthy life style benchmarks and the lack of the need to move make it necessary to provide feedback about physical and sedentary activities in order to promote active ways of life. The aim of this study was to develop a specific function adapted to overweight and obese people to identify four physical activity (PA) categories and to estimate the associated total energy expenditure (TEE). This function used accelerometry data collected from a smartphone to evaluate activity intensity and length, and TEE. The performance of the proposed function was estimated according to two references (Armband® and FitmatePro®) under controlled conditions (CC) for a 1.5-h scenario, and to the Armband® device in free-living conditions (FLC) over a 12-h monitoring period. The experiments were carried out with overweight and obese volunteers: 13 in CC and 27 in FLC. The evaluation differences in time spent in each category were lower than 7% in CC and 6% in FLC, in comparison to the Armband® and FitmatePro® references. The TEE mean gap in absolute value between the function and the two references was 9.3% and 11.5% in CC, and 8.5% according to Armband® in FLC.

Asunto(s)

RESUMEN

The proliferation of smartphones is creating new opportunities to monitor and interact with human subjects in free-living conditions since smartphones are familiar to large segments of the population and facilitate data collection, transmission and analysis. From accelerometry data collected by smartphones, the present work aims to estimate time spent in different activity categories and the energy expenditure in free-living conditions. Our research encompasses the definition of an energy-saving function (PredEE) considering four physical categories of activities (still, light, moderate and vigorous), their duration and metabolic cost (MET). To create an efficient discrimination function, the method consists of classifying accelerometry-transformed signals into categories and of associating each category with corresponding Metabolic Equivalent Tasks. The performance of the PredEE function was compared with two previously published functions (f(η,d)aedes,f(η,d)nrjsi), and with two dedicated sensors (Armband® and Actiheart®) in free-living conditions over a 12-h monitoring period using 30 volunteers. Compared to the two previous functions, PredEE was the only one able to provide estimations of time spent in each activity category. In relative value, all the activity categories were evaluated similarly to those given by Armband®. Compared to Actiheart®, the function underestimated still activities by 10.1% and overestimated light- and moderate-intensity activities by 7.9% and 4.2%, respectively. The total energy expenditure error produced by PredEE compared to Armband® was lower than those given by the two previous functions (5.7% vs. 14.1% and 17.0%). PredEE provides the user with an accurate physical activity feedback which should help self-monitoring in free-living conditions.

Asunto(s)

RESUMEN

Mountain endurance running has increased in popularity in recent years. Thus the aim of the present study was to determine if maximal oxygen uptake (VO2max) and energy cost of running (Cr) measured during level and uphill running are associated. Ten high level male endurance mountain runners performed three maximal oxygen uptake tests at three slope conditions (0, 12.5 and 25%). Metabolic data, step frequency (SF) and step length (SL) were recorded. No significant differences were found in VO2max (63.29 (±3.84), 63.97 (±3.54) and 63.70 (±3.58) mlO2/kg(-1)/min(-1)) or associated metabolic data at 0, 12.5 and 25% slope respectively. High intra-individual correlations were found between metabolic data measured in the three conditions. The energy cost of running was significantly different between slopes (0.192 (±0.01), 0.350 (±0.029) and 0.516 (±0.035) mlO2/kg(-1)/min(-1), p < 0.01), 0, 12.5 and 25% respectively. However, Cr0% was not correlated with either Cr25% or Cr12.5% (rs = 0.09 and rs = 0.10), in contrast, Cr25% and Cr12.5% were correlated (rs = 0.78). Step length was positively correlated with speed under the three slope conditions. Step frequency was significantly lower at 25 compared to 12.5 and 0% slope. We found that the maximum aerobic power did not differ between level and graded treadmill tests. However, the increase in Cr on the inclined versus level conditions varied between subjects. None of the measured anthropometric or kinematic variables could explain the higher increase in Cr of some subjects when running uphill. Thus, a short graded (5min at 12.5%) running test should be performed at a submaximal velocity (around 40% of level vVO2max) to enhance understanding of an endurance runner's uphill capability. Key pointsIn elite endurance mountain runners, there is no difference in VO2max values between level and uphill running.In a homogeneous group of mountain runners, uphill Cr is not associated with level Cr.To assess performance potential of endurance mountain runners, a standardized uphill running protocol should be performed.

RESUMEN

Recent laboratory studies have suggested that heart rate variability (HRV) may be an appropriate criterion for training load (TL) quantification. The aim of this study was to validate a novel HRV index that may be used to assess TL in field conditions. Eleven well-trained long-distance male runners performed four exercises of different duration and intensity. TL was evaluated using Foster and Banister methods. In addition, HRV measurements were performed 5 minutes before exercise and 5 and 30 minutes after exercise. We calculated HRV index (TLHRV) based on the ratio between HRV decrease during exercise and HRV increase during recovery. HRV decrease during exercise was strongly correlated with exercise intensity (R = -0.70; p < 0.01) but not with exercise duration or training volume. TLHRV index was correlated with Foster (R = 0.61; p = 0.01) and Banister (R = 0.57; p = 0.01) methods. This study confirms that HRV changes during exercise and recovery phase are affected by both intensity and physiological impact of the exercise. Since the TLHRV formula takes into account the disturbance and the return to homeostatic balance induced by exercise, this new method provides an objective and rational TL index. However, some simplification of the protocol measurement could be envisaged for field use.

Asunto(s)

RESUMEN

Rapid force production is critical to improve performance and prevent injuries. However, changes in rate of force/torque development caused by the repetition of maximal contractions have received little attention. The aim of this study was to determine the relative influence of rate of torque development (RTD) and peak torque (T(peak)) on the overall performance (i.e. mean torque, T(mean)) decrease during repeated maximal contractions and to investigate the contribution of contractile and neural mechanisms to the alteration of the various mechanical variables. Eleven well-trained men performed 20 sets of 6-s isokinetic maximal knee extensions at 240° · s(-1), beginning every 30 seconds. RTD, T(peak) and T(mean) as well as the Rate of EMG Rise (RER), peak EMG (EMG(peak)) and mean EMG (EMG(mean)) of the vastus lateralis were monitored for each contraction. A wavelet transform was also performed on raw EMG signal for instant mean frequency (if(mean)) calculation. A neuromuscular testing procedure was carried out before and immediately after the fatiguing protocol including evoked RTD (eRTD) and maximal evoked torque (eT(peak)) induced by high frequency doublet (100 Hz). T(mean) decrease was correlated to RTD and T(peak) decrease (R(²) = 0.62; p<0.001; respectively ß=0.62 and ß=0.19). RER, eRTD and initial if(mean) (0-225 ms) decreased after 20 sets (respectively -21.1 ± 14.1, -25 ± 13%, and ~20%). RTD decrease was correlated to RER decrease (R(²) = 0.36; p<0.05). The eT(peak) decreased significantly after 20 sets (24 ± 5%; p<0.05) contrary to EMG(peak) (-3.2 ± 19.5 %; p=0.71). Our results show that reductions of RTD explained part of the alterations of the overall performance during repeated moderate velocity maximal exercise. The reductions of RTD were associated to an impairment of the ability of the central nervous system to maximally activate the muscle in the first milliseconds of the contraction.

Asunto(s)

RESUMEN

The purpose of this study was to measure the influence of breathing frequency (BF) on heart rate variability (HRV) and specifically on the Low Frequency/High Frequency (LF/HF) ratio in athletes. Fifteen male athletes were subjected to HRV measurements under six randomised breathing conditions: spontaneous breathing frequency (SBF) and five others at controlled breathing frequencies (CBF) (0.20; 0.175; 0.15; 0.125 and 0.10 Hz). The subjects were divided in two groups: the first group included athletes with SBF <0.15 Hz (infSBF) and the second athletes with SBF higher than 0.15 Hz (supSBF). Fatigue and training load were evaluated using a validated questionnaire. There was no difference between the two groups for the fatigue questionnaire and training load. However, the LF/HF ratio during SBF was higher in infSBF than in supSBF (6.82 ± 4.55 vs. 0.72 ± 0.52; p<0.001). The SBF and LF/HF ratio were significantly correlated (R=-0.69; p=0.004). For the five CBF, no differences were found between groups; however, LF/HF ratios were very significantly different between sessions at 0.20; 0.175; 0.15 Hz and 0.125; 0.10 Hz. In this study, BF was the main modulator of the LF/HF ratio in both controlled breathing and spontaneous breathing. Although, none of the subjects of the infSBF group were overtrained, during SBF they all presented LF/HF ratios higher than four commonly interpreted as an overtraining syndrome. During each CBF, all athletes presented spectral energy mainly concentrated around their BF. Consequently, spectral energy was located either in LF or in HF band. These results demonstrate that the LF/HF ratio is unreliable for studying athletes presenting SBF close to 0.15 Hz leading to misclassification in fatigue.

Asunto(s)

RESUMEN

The study examined the fatigue effect on tennis performance and upper limb muscle activity. Ten players were tested before and after a strenuous tennis exercise. Velocity and accuracy of serve and forehand drives, as well as corresponding surface electromyographic (EMG) activity of eight upper limb muscles were measured. EMG and force were also evaluated during isometric maximal voluntary contractions (IMVC). Significant decreases were observed after exercise in serve accuracy (-11.7%) and velocity (-4.5%), forehand accuracy (-25.6%) and consistency (-15.6%), as well as pectoralis major (PM) and flexor carpi radialis (FCR) IMVC strength (-13.0% and -8.2%, respectively). EMG amplitude decreased for PM and FCR in serve, forehand and IMVC, and for extensor carpi radialis in forehand. No modification was observed in EMG activation timing during strokes or in EMG frequency content during IMVC. Several hypotheses can be put forward to explain these results. First, muscle fatigue may induce a reduction in activation level of PM and forearm muscles, which could decrease performance. Second, conscious or subconscious strategies could lead to a redistribution of muscle activity to non-fatigued muscles in order to protect the organism and/or limit performance losses. Otherwise, the modifications of EMG activity could also illustrate the strategies adopted to manage the speed-accuracy trade-off in such a complex task.

Asunto(s)

RESUMEN

The purpose of the present work was to compare daily variations of heart rate variability (HRV) parameters between controlled breathing (CB) and spontaneous breathing (SB) sessions during a longitudinal follow-up of athletes. HRV measurements were performed daily on 10 healthy male runners for 21 consecutive days. The signals were recorded during two successive randomised 5-minutes sessions. One session was performed in CB and the other in SB. The results showed significant differences between the two respiration methods in the temporal, nonlinear and frequency domains. However, significant correlations were observed between CB and SB (higher than 0.70 for RMSSD and SD1), demonstrating that during a longitudinal follow-up, these markers provide the same HRV variations regardless of breathing pattern. By contrast, independent day-to-day variations were observed with HF and LF/HF frequency markers, indicating no significant relationship between SB and CB data over time. Therefore, we consider that SB and CB may be used for HRV longitudinal follow-ups only for temporal and nonlinear markers. Indeed, the same daily increases and decreases were observed whatever the breathing method employed. Conversely, frequency markers did not provide the same variations between SB and CB and we propose that these indicators are not reliable enough to be used for day-to-day HRV monitoring.

Asunto(s)